计算机工程 ›› 2009, Vol. 35 ›› Issue (16): 20-22.doi: 10.3969/j.issn.1000-3428.2009.16.007

• 博士论文 • 上一篇    下一篇

数字彩色图像拷贝-变换-移动篡改检测

王 鑫1,轩 波2,彭思龙2   

  1. (1. 解放军信息工程大学应用数学系,郑州 450002;2. 中国科学院自动化研究所,北京 100080)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-08-20 发布日期:2009-08-20

Detection of Copy-Transform-Move Forgery in Color Digital Image

WANG Xin1, XUAN Bo2, PENG Si-long2   

  1. (1. Dept. of Application Mathematics, PLA Information Engineering University, Zhengzhou 450002;2. Institute of Automation, Chinese Academy of Sciences, Beijing 100080)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-08-20 Published:2009-08-20

摘要: 针对拷贝-变换-移动篡改技术,提出基于尺度不变特征变换(SIFT)特征点的检测算法。该算法利用快速匹配方法得到互相匹配的SIFT特征点作为种子点,根据SIFT特征点的尺度和方向信息制定合适的生长策略逐步生长出被篡改区域。实验结果证明,该算法对常用的润色操作和JPEG压缩有较好的稳健性。

关键词: 图像取证, 图像篡改, 拷贝-移动篡改, 拷贝-变换-移动篡改, 尺度不变特征变换

Abstract: This paper studies copy-transform-move forgery and proposes a detection method. The method is based on matching Scale Invariant Feature Transform(SIFT) points in the same image. The method designs a fast matching method to find matching points. The forged regions grow up stepwise based on an appropriate region growing strategy with matching SIFT points as seed-points. The method is robust to common retouch tools and JPEG compression.

Key words: image forensics, image forgery, copy-move forgery, copy-transform-move forgery, Scale Invariant Feature Transform(SIFT)

中图分类号: